Classification of Citrus Plant Diseases Using Deep Transfer Learning

作     者：Muhammad Zia Ur Rehman Fawad Ahmed Muhammad Attique Khan Usman Tariq Sajjad Shaukat Jamal Jawad Ahmad Iqtadar Hussain 

作者机构：Department of Electrical EngineeringHITEC UniversityTaxilaPakistan Department of Computer ScienceHITEC UniversityTaxilaPakistan College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAl-KhrajSaudi Arabia Department of MathematicsCollege of ScienceKing Khalid UniversityAbhaSaudi Arabia School of ComputingEdinburgh Napier UniversityUK Department of MathematicsStatisticsand PhysicsQatar UniversityDoha2713Qatar 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第70卷第1期

页      面：1401-1417页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Deanship of Scientific Research  King Faisal University  DSR  KFU  (R. G. P. 1/77/42) 

主　　题：Citrus plant disease classification deep learning feature fusion deep transfer learning 

摘      要：In recent years,the field of deep learning has played an important role towards automatic detection and classification of diseases in vegetables and *** in turn has helped in improving the quality and production of vegetables and *** fruits arewell known for their taste and nutritional *** are one of the natural and well known sources of vitamin C and planted *** are several diseases which severely affect the quality and yield of citrus *** this paper,a new deep learning based technique is proposed for citrus disease *** different pre-trained deep learning models have been used in this *** increase the size of the citrus dataset used in this paper,image augmentation techniques are ***,to improve the visual quality of images,hybrid contrast stretching has been *** addition,transfer learning is used to retrain the pre-trainedmodels and the feature set is enriched by using feature *** fused feature set is optimized using a meta-heuristic algorithm,the Whale Optimization Algorithm(WOA).The selected features are used for the classification of six different diseases of citrus *** proposed technique attains a classification accuracy of 95.7%with superior results when compared with recent techniques.